AI & Agents
Poly
Last updated 2026-08-04 · benchmark measured 2026-08-09 — deterministic & reproducible
Poly is a shared coding room where teams collaboratively steer one Claude Code agent.
Is Poly production-ready?
Legit.Show scores Poly 69 out of 100 — the simple average of its 4 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Poly (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Privacy. 4 of the seven frames returned a score; Security, Reliability and Discoverability were not measurable on this service and are recorded as null — not as zero. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 85/100
- Accessibility — 96/100
- Security — not measurable on this service (null — not scored as 0)
- Privacy — 25/100
- Reliability — not measurable on this service (null — not scored as 0)
- Standards — 70/100
- Discoverability — not measurable on this service (null — not scored as 0)
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 0 ms to first byte.
- 0 of 0 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: sitemap.
Who it's for
Development teams · Software engineers · Collaborative coding groups · Remote teams · Claude users
Pricing
Free to sign up, pay-as-you-go per Claude API usage (e.g., $0.09 per turn example shown)
Visit Poly → · Alternatives to Poly → · How this was measured →